基于机器视觉的田间杂草识别技术研究进展

Research advances of weed identification technology using machine vision

田间杂草识别技术是实现变量喷洒除草剂以保护环境的关键所在。针对国内外在精细农业的杂草识别领域,全面、系统地分析了基于机器视觉的田间杂草识别技术的研究进展与应用状况,以促进该项技术在中国的应用和发展。分别阐述了利用植物和背景形状特征、纹理特征、颜色特征和多光谱特征识别田间杂草技术的理论依据、特征参数、研究状况和问题所在,并指出了实现田间实时识别的难点。

Weed identification technology is the key to the realization of selectively spraying herbicide for the environmental protection. In order to promote the research and application of this technology in China, the research methods and advances of weed identification technology using machine vision in precision farming were analyzed. The theory, feature parameters, research advances and problems using the shape, texture, color and multi-spectral features to identify weed were discussed, respectively. The difficulties of real-time identification were concluded.